JPH07319878A - Machine translating device - Google Patents

Abstract

PURPOSE:To improve work efficiency and the validity of a processing by permitting a user to arbitrarily designate the display system of a detection result (unknown word list) in the detection of an unknown word for detecting a word (unknown word) which does not exist in a dictionary. CONSTITUTION:In addition to a conventional machine translating device, an input means 1 including a means designating the display system of the unknown word list by the user, an unknown word ilst system conversion means 5 rearranging the appearing order, the alphabetical order and the frequent order of the unknown word lists and adding appearing frequency or important degrees to the rearranged unknown word lists and an important degree calculation means 6 calculating the important degree based on the appearing frequency of the respective unknown words are provided.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a machine translation device for converting an input in one language into a different language.

[0002]

2. Description of the Related Art In a machine translation device for translating one language into a different language, in order to properly perform translation, words in an input document do not include words that do not exist in the dictionary used by the machine translation device. Is a necessary condition.

In a conventional machine translation apparatus, an unknown word detection operation of detecting an unknown word not registered in the dictionary is performed on an input document by referring to a dictionary such as a word dictionary or a user dictionary created by a user. Then, the detected unknown word is displayed, and for each unknown word, the user performs an unknown word processing operation such as registration in the user dictionary or spelling correction of the word.

[0004]

However, when a large number of unknown words exist, it may not be possible to finish all the processing within a limited time. Since the user cannot specify the display method of, it is not possible to select a display method that is easier to perform according to the processing.
Unless the user intentionally selected from the list, it was not possible to perform processing from unknown words of higher importance.

The present invention solves the above problem and allows the user to arbitrarily specify the display format of the detection result (unknown word list), thereby improving work efficiency and processing effectiveness. An object is to provide a machine translation device.

[0006]

In order to solve the above problems, the machine translation apparatus of the present invention has an unknown word detecting means for detecting an unknown word that does not exist in a dictionary, which is included in a conventional machine translation apparatus, and an unknown word detecting means. In addition to the unknown word storage means for storing words and the means for displaying the result of detecting an unknown word (unknown word list), the user specifies the display format of the unknown word list, and according to the user's instruction, Order of appearance of unknown word list,
An unknown word list format conversion means for rearranging in alphabetical order, frequency order, and adding the appearance frequency or importance to the rearranged unknown word list, and the above-mentioned important from the appearance frequency of each unknown word It has an importance degree calculating means for calculating the degree.

[0007]

In this structure, the unknown word detected by the unknown word detection means is stored in the unknown word storage means and displayed by the display means. When the display format is specified by the user by the input means, The unknown word list format conversion means and the importance degree calculation means convert the format of the unknown word list, and the display means redisplays. This allows
The user can improve work efficiency.

[0008]

DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a functional block diagram of a machine translation device according to an embodiment of the present invention. In FIG. 1, reference numeral 1 denotes an input means for inputting an original sentence, an unknown word detection instruction, an unknown word list display format instruction, spelling correction as unknown word processing, translation execution instruction, and word registration in a user dictionary. Two
Is an original sentence that stores the original sentence input by the input unit 1 and the translation result by the translation execution unit 9 described later in association with each other.
The translated text storage unit 3 refers to the original text stored in the original text / translated text storage unit 2 while referring to a dictionary group, and an unknown word detection unit that detects words (unknown words) not registered in all dictionaries.
Reference numeral 4 is an unknown word storage unit for storing the unknown word detected by the unknown word detection unit 3 and its appearance position data, and 5 is an unknown word storage unit when the input means 1 gives an instruction for an unknown word list display format. 4. The unknown words stored in 4 are rearranged in the order of appearance, alphabetical order, frequency, and the rearranged unknown word list, the appearance frequency or the degree of importance obtained from the importance degree calculation unit 6 described later. Unknown word list format conversion unit 6 for adding
From the appearance frequency of each unknown word stored in the unknown word storage unit 4,
An importance degree calculation unit for calculating the importance degree, 7 is performed for an unknown word stored in the unknown word storage unit 4, registration of an unknown word in a user dictionary by a user dictionary registration unit 8 to be described later, and an input means 1 An unknown word processing management unit that manages processes such as spelling correction of unknown words, and that deletes the processed unknown words from the unknown words stored in the unknown word storage unit 4;
Is a user dictionary registration unit that stores information on words necessary for translation, such as headings and translations, in a user dictionary 12 described below while interacting with the user when the user instructs registration of the user dictionary, and 9 is a rule dictionary described below. 13, word dictionary 11,
A translation execution unit 10 that refers to the user dictionary 12 and translates the original sentence stored in the original sentence / translated sentence storage unit 2 performs an unknown word list processed by the unknown word list format conversion unit 5 and unknown word processing. Screen, display means for displaying a registration screen for registering words in the user dictionary, 11 a word dictionary storing information about words necessary for translation, and 12 storing information about words necessary for translation. A user dictionary that is rewritable by the user, 13 is a rule dictionary that stores information about grammar necessary for translation, and 14 is input means 1
The inputted original sentence is stored in the original sentence / translated sentence storage unit 2, and when the unknown word detection is instructed, the original sentence stored in the original sentence / translated sentence storage unit 2 is passed to the unknown word detection unit 3 and the unknown word list is displayed. When the format is instructed, the unknown word list format conversion unit 5 is controlled, the list of the instructed format is passed to the display means 10, and the contents of the original sentence / translated sentence storage unit 2 are changed according to the processing by the unknown word processing management unit 5. When a change is made and a translation is instructed, the original sentence stored in the original sentence / translated sentence storage unit 2 is passed to the translation execution unit 9, and the translated sentence of the execution result is stored in the original sentence / translated sentence storage unit 2, and between the functions. Is a control unit for controlling the operation of.

FIG. 2 is a circuit block diagram of the machine translation apparatus of this embodiment. In FIG. 2, 15 is a keyboard, 1
6 is a central processing unit (hereinafter abbreviated as CPU), 17 is a cathode ray tube display (hereinafter abbreviated as CRT), 18 is a read-only memory (hereinafter abbreviated as ROM), 19
Is a random access memory (hereinafter abbreviated as RAM).

The input means 1 shown in FIG. 1 is a keyboard 15
Accordingly, the original sentence / translated sentence storage unit 2, the unknown word storage unit 4, the user dictionary 12 is stored in the RAM 19, the word dictionary 11 and the rule dictionary 13 are stored in the ROM 18, and the unknown word detection unit 3, the unknown word list format conversion unit 5, and the importance calculation are performed. The unit 6, the unknown word processing management unit 7, the user dictionary registration unit 8, the translation execution unit 9, and the control unit 14 are displayed by the CPU 16 that executes the program stored in the ROM 18 while exchanging data with the ROM 18 and the RAM 19. The means 10 is implemented by the CRT 17.

The operation of the machine translation apparatus of this embodiment constructed as described above will be described below with reference to the flowchart of FIG. First, in step S1, the translation target document is input from the input unit 1. The input document is the control unit 14
Are stored in the original / translated sentence storage unit 2. Step S2
When an instruction to detect an unknown word is given from the input means 1,
Go to step S3. When the instruction to detect the unknown word is not issued, the following unknown word detection and unknown word processing are not performed, and the process proceeds to step S14.

In step S3, a word (unknown word) that does not exist in the word dictionary 11 and the user dictionary 12 is detected for the original sentence stored in the original sentence / translated sentence storage unit 2. The list of detected unknown words is stored in the unknown word storage unit 4.
In step S4, the display unit 10 displays the result of unknown word detection performed in step S3 under the control of the control unit 14. When the input means 1 instructs the unknown word list display format in step S5, the process proceeds to step S6. In step S6, the unknown word list format conversion unit 6 converts the unknown word stored in the unknown word storage unit 4 into the format instructed in step S5, and the process returns to step S4 to perform the format conversion of the unknown word. Display the detection results.

The format conversion of the unknown word list in step S6 will be described with reference to the flowchart of FIG. In step 6A, if the instruction form from the input means 1 in step S5 is the order of appearance, the process proceeds to step 6B, and if not, the process proceeds to step 6C. Step 6
In B, the unknown words stored in the unknown word storage unit 4 are rearranged in the order of appearance by referring to the appearance position data, and the step 6G is executed.
Go to. In step 6C, if the instruction format in step S5 is in alphabetical order, the process proceeds to step 6D, and if not, the process proceeds to step 6E. Step 6
In D, the unknown words stored in the unknown word storage unit 4 are rearranged in alphabetical order, and the process proceeds to step 6G. In step 6E, if the instruction format in step S5 is not in the frequency order, the process directly proceeds to step 6G, and if it is in the frequency order, the process proceeds to step 6F. In step 6F, the unknown word storage unit 4
The unknown words stored in 1 are sorted in order from the one having the same number of appearances of the unknown word, and the process proceeds to step 6G.

In step 6G, if the instruction in step S5 is to change the frequency display, the process proceeds to step 6H. Otherwise, the following process is not performed and the process of converting the unknown word list format is terminated. .

In step 6H, if the instruction in step S5 is to turn off the frequency display, the process proceeds to step 6I. If not, the process proceeds to step 6J. In step 6I, the frequency assigned to the unknown word list is cleared.
In step 6J, the appearance frequency of each unknown word is counted. In step 6K, if the instruction in step S5 is the display of the frequency, the process proceeds to step 6L, and if it is the display of the importance, the process proceeds to step 6M. In step 6L, the frequency is added to the unknown word list. In step 6M, the importance calculator calculates the importance of the unknown word from the appearance frequency of each unknown word counted in step 6J,
Proceed to N. At step 6N, importance is given to the unknown word list. This completes the process of converting the unknown word list format.

If no display format is designated in step S5, the process proceeds to step S7. When an instruction to end the unknown word processing is issued from the input means 1 in step S7, the unknown word processing is not performed and the process proceeds to the translation in step S14.

Steps S8 to S13 are unknown word processing performed under the management of the unknown word processing management section 7. First, in step S8, the input means 1 instructs which of the displayed unknown words is to be processed. In step S9, when the user dictionary is instructed from the input means 1, the process proceeds to step S10. In step S10, the user dictionary registration unit 7 registers the user dictionary of the word designated in step S8 while interacting with the user using the input means and the output means 9. When the user dictionary registration is not instructed in step S9, the user determines that the word originally exists in the dictionary but is misspelled and thus becomes an unknown word, and the process proceeds to step S11. Step S11
Then, the correct spelling of the word instructed in step S8 is input by the input means 1 to make a correction. Step S12
Then, the unknown word processing management unit 7 deletes the processed word from the unknown word list stored in the unknown word storage unit 4. In step S13, if there is no instruction to end the unknown word processing from the input means 1, the process returns to step S5 and the unknown word processing is performed.

In step S13, if there is an instruction to end the unknown word processing, the process proceeds to step S14. If there is a translation instruction from the input means 1, the translation execution unit 9 translates and the processing ends.

[0019]

As described above, according to the present invention, when processing an unknown word that does not exist in the dictionary, the user can arbitrarily specify the display format of the unknown word list. The display format can be changed according to the content of the process, and the work efficiency is improved. In addition, by clearly indicating the frequency of occurrence and the degree of importance, it is possible to easily perform processing from important unknown words with high frequency of occurrence, and it is possible to improve the effectiveness of processing by the user within a limited time. .

[Brief description of drawings]

FIG. 1 is a functional block diagram of a machine translation device according to an embodiment of the present invention.

FIG. 2 is a circuit block diagram of a machine translation device according to an embodiment of the present invention.

FIG. 3 is a flowchart showing the operation of the machine translation device according to the embodiment of the present invention.

FIG. 4 is a flowchart showing the operation of the unknown word list format conversion unit of the machine translation device in one embodiment of the present invention.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Input means 2 Original sentence / translated sentence storage section 3 Unknown word detection section 4 Unknown word storage section 5 Unknown word list format conversion section 6 Importance calculation section 7 Unknown word processing management section 8 User dictionary registration section 9 Translation execution section 10 Display means 11 Word dictionary 12 User dictionary 13 Rule dictionary 14 Control unit 15 Keyboard 16 CPU 17 CRT 18 ROM 19 RAM

Claims (7)

[Claims] 1. An input means for inputting an original sentence, an instruction for detecting an unknown word, a spelling correction as an unknown word process, an instruction for executing a translation, and a word registration in a user dictionary, and an original sentence and a translation result are associated with each other. An original sentence / translated sentence storage unit to be stored, and an unknown word detection unit to detect a word (unknown word) that is not registered in all dictionaries while referring to a dictionary group with respect to the original sentence stored in the original sentence / translated sentence storage unit, The unknown word storage unit that stores the detected unknown word and its appearance position data, the unknown word list format conversion unit that converts the formation of the list of unknown words stored in the unknown word storage unit, and the unknown word storage unit Manages unknown words stored in the user dictionary, spelling corrections for unknown words, and deletes unknown words from unknown words stored in the unknown word storage unit. The unknown word processing management unit that performs processing A group of dictionaries that store information about words necessary for translation (word dictionaries that users cannot change, and
A user dictionary rewritable by the user), and a user dictionary registration unit for storing information on words necessary for translation such as headings and translated words in the user dictionary while interacting with the user when the user instructs registration of the user dictionary. A machine having display means for displaying an unknown word list as a result of unknown word detection, a screen for performing unknown word processing, and a registration screen for performing word registration in a user dictionary Translation device. 2. The unknown word list format conversion unit for converting the format of the list of unknown words stored in the unknown word storage unit, rearranges the unknown words in the order of appearance and displays them on the display means. 1. The machine translation device according to 1. 3. The unknown word list format conversion unit for converting the format of the list of unknown words stored in the unknown word storage unit displays the unknown words in alphabetical order on the display means. 1. The machine translation device according to 1. 4. The unknown word list format conversion unit for converting the format of the list of unknown words stored in the unknown word storage unit, rearranges the unknown words in frequency order and displays them on the display means. 1. The machine translation device according to 1. 5. The unknown word list format conversion unit for converting the format of the unknown word list stored in the unknown word storage unit adds the appearance frequency of each unknown word to the unknown word list and displays it on the display means. The machine translation device according to any one of claims 2 to 4, wherein: 6. An unknown word list which has an importance degree calculating unit for calculating the importance degree of each unknown word from the appearance frequency of each unknown word, and which converts the format of the list of unknown words stored in the unknown word storage unit. 6. The format conversion unit adds the importance of each unknown word to the unknown word list and displays it on the display means.
The machine translation device described. 7. The unknown word list format conversion unit for converting the format of the unknown word list stored in the unknown word storage unit by the user having a unit for designating the display format of the unknown word list is a user instruction. According to claim 2,
6. The machine translation apparatus according to claim 1, wherein the machine translation apparatus converts the format into any one of the formats and displays the format on a display unit.